Computer Vision

Course topics

Part 1. Correspondence of Local Features

  • Local features: introduction, terminology
  • Motivation: a generalization of local stereo to wide-baseline stereo
  • Detection of Local invariant features
  • Descriptors, Matching
  • Correspondence Verification
  • RANSAC (robust model fitting)

Part 2. Tracking

  • Template Matching and the Lucas-Kanade Method
  • Mean Shift HW

Part 3. Graphical Models

  • Probabilistic models. Decisions under uncertainty
  • Hidden Markov Model. Markov chain, different factorizations. MAP problem — Viterbi algorithm
  • Marginals problem — forward-backward algorithm
  • Generalized dynamic programming
  • Markov Random Field. MAP in MRF
  • Energy minimization, solvable classes, graph cuts, relaxations
  • Graphical models as neural networks. Sigmoid Belief network
  • Uncertainties, noises
  • Variance propagation methods
  • Bayesian Learning. Variational Bayesian learning

Part 4. Geometry

  • Perspective camera model and calibration
  • Homography between two images
  • Projection and homography
  • Epipolar geometry and camera motion
  • 3D Reconstruction
  • Epipolar geometry and 3D reconstruction

Part 5. Retrieval

  • Image Retrieval
  • K-Means
  • Min-hash

Part 6. Deep Learning for Computer Vision

Part 7. Advanced CNN Topologies

Prerequisites

Ключові факти